In recent years, we have seen significant advances in different fields such as Computer Vision and Natural Language Processing as the result of Deep Learning. Can we also use Deep (Reinforcement) Learning to solve practical (combinatorial) optimization problems, such as the Travelling Salesman Problem (TSP)? I will take you through a recent example of how to use Deep Reinforcement Learning to learn a heuristic algorithm capable of finding good solutions quickly for the TSP and other routing problems.